Communicating Information Via A Computer-Implemented Agent

Abstract

Techniques and systems for communicating information via a computer-implemented agent are described. A computing device may obtain sensor data of an individual, such as visual data, audible data, physiological data, or combinations thereof. An emotional state of the individual may be determined based on the sensor data. A communications framework may be identified based on the emotional state of the individual. The communications framework may indicate a manner in which the computer-implemented agent communicates information to the individual. For example, the communications framework may specify voice features, facial features, body language, positioning in the environment, or combinations thereof, that may be utilized to produce a representation of a computer-implemented agent that communicates information to the individual. In some cases, the individual may provide feedback indicating a preference to have the computer-implemented agent communicate information in a different manner.

What is claimed is: 
     
         1 . A computing device comprising:
 one or more processors; and   one or more computer-readable storage media storing instructions that are executable by the one or more processors to perform operations comprising:
 identifying information to communicate to an individual; 
 obtaining electroencephalography (EEG) data of the individual, the EEG data including a pattern of EEG data over a period of time; 
 determining, based at least partly on the EEG data, an emotional state of the individual during the period of time; 
 identifying a plurality of communication frameworks that are stored in a data store in association with the individual, a communication framework of the plurality of communication frameworks indicating visual features and audible features of a computer-implemented agent; 
 determining that the communication framework corresponds to the emotional state of the individual; and 
 generating representation data indicating a representation of the computer-implemented agent based at least partly on the communication framework. 
   
     
     
         2 . The computing device of  claim 1 , wherein the representation data corresponds to one or more images of the representation of the computer-implemented agent, the one or more images including the visual features of the communication framework, and the visual features including facial expressions, gestures, body movements, body characteristics, or combinations thereof. 
     
     
         3 . The computing device of  claim 1 , wherein the representation data corresponds to one or more sounds, one or more words, or both of the representation of the computer-implemented agent, the one or more sounds, the one or more words, or both are based at least partly on the audible features of the communication framework. 
     
     
         4 . The computing device of  claim 1 , wherein the operations further comprise:
 obtaining feedback regarding one or more interactions between the individual and the computer-implemented agent related to the computer-implemented agent providing the information to be communicated to the individual; and   modifying a feature of the communication framework based at least partly on the feedback.   
     
     
         5 . The computing device of  claim 1 , wherein the communication framework includes first values for facial features of the computer-implemented agent and second values for voice features of the computer-implemented agent. 
     
     
         6 . The computing device of  claim 5 , wherein generating the representation data of the computer-implemented agent includes determining an appearance of a face of the representation of the computer-implemented agent according to the first values for the facial features of the computer-implemented agent and determining voice characteristics of the computer-implemented agent based at least partly on the second values for the voice features of the computer-implemented agent. 
     
     
         7 . The computing device of  claim 1 , wherein:
 a first communication framework of the plurality of communication frameworks corresponds to a first emotional state and is associated with a first pattern of EEG data;   a second communication framework of the plurality of communication frameworks corresponds to a second emotional state and is associated with a second pattern of EEG data different from the first pattern of EEG data; and   the method further comprises:
 comparing the EEG data of the individual to the first pattern of EEG data and the second pattern of EEG data; and 
 determining the emotional state of the individual during the period of time includes determining that a threshold amount of the EEG data of the individual corresponds to the first pattern of EEG data. 
   
     
     
         8 . A method comprising:
 obtaining, by a computing device including a processor and memory, sensor data for an individual, the sensor data including electroencephalography (EEG) data;   determining, by the computing device, an emotional state of the individual based at least partly on the sensor data;   determining, by the computing device, a communication framework that corresponds to the emotional state of the individual, the communication framework indicating visual features and audible features of a computer-implemented agent; and   generating, by the computing device, representation data indicating a representation of the computer-implemented agent based at least partly on the communication framework.   
     
     
         9 . The method of  claim 8 , wherein determining the emotional state of the individual includes:
 comparing the EEG data with predetermined benchmark EEG data that indicates a plurality of emotional states; and   determining that a threshold amount of the EEG data corresponds with a portion of the predetermined benchmark EEG data associated with the emotional state.   
     
     
         10 . The method of  claim 8 , wherein:
 the sensor data includes one or more images of the individual; and   determining the emotional state of the individual based at least partly on the sensor data further comprises:
 determining, based at least partly on the one or more images of the individual, characteristics of one or more facial features of the individual; 
 comparing the characteristics of the one or more facial features of the individual to predetermined benchmark image data that indicates a plurality of emotional states; and 
 determining that a threshold amount of the characteristics of the one or more facial features of the individual correspond to a portion of the predetermined benchmark image data associated with the emotional state. 
   
     
     
         11 . The method of  claim 8 , wherein:
 the sensor data includes audible data of the individual, the audible data including at least one of one or more sounds or one or more words; and   determining the emotional state of the individual based at least partly on the sensor data further comprises:
 determining characteristics of one or more voice features of the individual based at least partly on the audible data; 
 comparing the characteristics of the one or more voice features of the individual to predetermined benchmark audible data that indicates a plurality of emotional states; and 
 determining that a threshold amount of the characteristics of the one or more voice features of the individual correspond to a portion of the predetermined benchmark audible data associated with the emotional state. 
   
     
     
         12 . The method of  claim 8 , wherein the sensor data is obtained from an electronic device via one or more networks, and the method further comprises:
 sending the representation data to the electronic device.   
     
     
         13 . The method of  claim 12 , further comprising:
 receiving feedback from the electronic device, the feedback corresponding to one or more interactions between the individual and the computer-implemented agent; and   modifying the communication framework based at least partly on the feedback.   
     
     
         14 . The method of  claim 13 , wherein receiving feedback from the electronic device includes receiving audible information including at least one of words or sounds related to the one or more interactions between the individual and the computer-implemented agent. 
     
     
         15 . A computing device comprising:
 one or more processors; and   one or more computer-readable storage media storing instructions that are executable by the one or more processors to perform operations comprising:
 obtaining sensor data including at least one of visual data associated with an individual, audible data associated with the individual, or electroencephalography (EEG) data associated with the individual; 
 determining an emotional state of the individual based at least partly on the sensor data; 
 determining a communication framework that corresponds to the emotional state of the individual, the communication framework indicating visual features and audible features of a computer-implemented agent; 
 generating representation data indicating a representation of the computer-implemented agent based at least partly on the communication framework; 
 obtaining feedback regarding communication of information by the computer-implemented agent to the individual; and 
 modifying a feature of the communication framework based at least partly on the feedback. 
   
     
     
         16 . The computing device of  claim 15 , wherein the operations further comprise:
 obtaining data from an electronic device, the data indicating the feedback of the individual regarding one or more interactions between the computer-implemented agent and the individual.   
     
     
         17 . The computing device of  claim 16 , wherein the operations further comprise:
 determining that the data obtained from the electronic device is associated with the feedback by comparing the data to predetermined feedback data, the predetermined feedback data indicating one or more voice features that correspond to user feedback, one or more facial features that correspond to user feedback, one or more gestures that correspond to user feedback, one or more body movements that correspond to user feedback, or combinations thereof.   
     
     
         18 . The computing device of  claim 15 , wherein the feedback is related to at least one of:
 voice features of the computer-implemented agent;   facial features of the computer-implemented agent;   body language of the computer-implemented agent; or   positioning of the computer-implemented agent within an environment that includes the individual.   
     
     
         19 . The computing device of  claim 18 , wherein modifying the feature of the communication framework based at least partly on the feedback includes modifying values of the communication framework associated with at least one of the voice features of the computer-implemented agent, the facial features of the computer-implemented agent, the body language of the computer-implemented agent, or the positioning of the computer-implemented agent within the environment that includes the individual. 
     
     
         20 . The computing device of  claim 15 , wherein obtaining the feedback includes determining that the feedback is provided within a threshold period of time after an interaction between the computer-implemented agent and the individual.